# VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping Source: [VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping]() Collection index: [llms.txt]() Data updated: 2026-02-21T05:00:04.173Z Authors: Sanoojan Baliah, Yohan Abeysinghe, Rusiru Thushara, Khan Muhammad, Abhinav Dhall, Karthik Nandakumar, Muhammad Haris Khan Published: 2026-02-08T06:13:19.000Z ## Abstract We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion models. First, we introduce a Frequency Spectrum Attention Interpolation technique to facilitate generation and intact key identity characteristics. Second, we achieve Target Structure Guidance via plug-and-play attention injection to better align the structural features from the target frame to the generation. Third, we present a Flow-Guided Attention Temporal Smoothening mechanism that enforces spatiotemporal coherence without modifying the underlying diffusion model to reduce temporal inconsistencies typically encountered in frame-wise generation. Our method requires no additional training or video-specific fine-tuning. Extensive experiments show that our method significantly enhances temporal consistency and visual fidelity, offering a practical and modular solution for video-based face swapping. Our code is available at https://github.com/Sanoojan/VFace. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Face Swapping on CelebA (test)](): Face Swapping; CelebA (test); FID: 5.42. - [Face Swapping on FFHQ](): Face Swapping; FFHQ; FID: 4.29. ## Original sources and implementation [Original paper]() [PDF]()